This work presents methodology based on the use of nuclear technique and artificial intelligence for attainment of volume fractions in stratified and annular multiphase flow regime, oil-water-gas, very frequent in the offshore industry petroliferous. Using the principles of absorption and scattering of gamma-rays and an
adequate geometry scheme of detection with two detectors and two energies measurement are gotten and they vary as changes in the volume fractions of flow regime occur. The MCNP-X code was used in order to provide the data training for artificial neural network that matched such information with the respective actual volume fractions of each material.